INDEX

Explanations

code-related operations and function calls

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GenerationType

-0.78

 morire

-0.73

 réfugiés

-0.71

 defStyleAttr

-0.70

 contextLoads

-0.66

 المعيارى

-0.63

 refusé

-0.62

Rhestr

-0.61

StoreMessageInfo

-0.61

 leçons

-0.61

POSITIVE LOGITS

 said

0.60

+=

0.58

 write

0.55

 says

0.54

 continued

0.54

 wrote

0.53

append

0.52

}}}\

0.52

Indent

0.49

 emphas

0.48

Activations Density 0.082%

code-related operations and function calls

No Comments

No Known Activations